*/
static bool create_on_open = true;
-/* bio_clone_mddev
- * like bio_clone_bioset, but with a local bio set
- */
-
struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
struct mddev *mddev)
{
static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
{
const int rw = bio_data_dir(bio);
+ const int sgrp = op_stat_group(bio_op(bio));
struct mddev *mddev = q->queuedata;
unsigned int sectors;
int cpu;
md_handle_request(mddev, bio);
cpu = part_stat_lock();
- part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
- part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
+ part_stat_inc(cpu, &mddev->gendisk->part0, ios[sgrp]);
+ part_stat_add(cpu, &mddev->gendisk->part0, sectors[sgrp], sectors);
part_stat_unlock();
return BLK_QC_T_NONE;
rdev_dec_pending(rdev, mddev);
if (atomic_dec_and_test(&fi->flush_pending)) {
- if (bio->bi_iter.bi_size == 0)
+ if (bio->bi_iter.bi_size == 0) {
/* an empty barrier - all done */
bio_endio(bio);
- else {
+ mempool_free(fi, mddev->flush_pool);
+ } else {
INIT_WORK(&fi->flush_work, submit_flushes);
queue_work(md_wq, &fi->flush_work);
}
rcu_read_unlock();
if (atomic_dec_and_test(&fi->flush_pending)) {
- if (bio->bi_iter.bi_size == 0)
+ if (bio->bi_iter.bi_size == 0) {
/* an empty barrier - all done */
bio_endio(bio);
- else {
+ mempool_free(fi, mddev->flush_pool);
+ } else {
INIT_WORK(&fi->flush_work, submit_flushes);
queue_work(md_wq, &fi->flush_work);
}
if (mddev->queue)
blk_add_trace_msg(mddev->queue, "md md_update_sb");
rewrite:
- bitmap_update_sb(mddev->bitmap);
+ md_bitmap_update_sb(mddev->bitmap);
rdev_for_each(rdev, mddev) {
char b[BDEVNAME_SIZE];
if (buf == end) break;
}
if (*end && !isspace(*end)) break;
- bitmap_dirty_bits(mddev->bitmap, chunk, end_chunk);
+ md_bitmap_dirty_bits(mddev->bitmap, chunk, end_chunk);
buf = skip_spaces(end);
}
- bitmap_unplug(mddev->bitmap); /* flush the bits to disk */
+ md_bitmap_unplug(mddev->bitmap); /* flush the bits to disk */
out:
mddev_unlock(mddev);
return len;
else
pr_warn("md: personality for level %s is not loaded!\n",
mddev->clevel);
- return -EINVAL;
+ err = -EINVAL;
+ goto abort;
}
spin_unlock(&pers_lock);
if (mddev->level != pers->level) {
pers->start_reshape == NULL) {
/* This personality cannot handle reshaping... */
module_put(pers->owner);
- return -EINVAL;
+ err = -EINVAL;
+ goto abort;
}
if (pers->sync_request) {
(mddev->bitmap_info.file || mddev->bitmap_info.offset)) {
struct bitmap *bitmap;
- bitmap = bitmap_create(mddev, -1);
+ bitmap = md_bitmap_create(mddev, -1);
if (IS_ERR(bitmap)) {
err = PTR_ERR(bitmap);
pr_warn("%s: failed to create bitmap (%d)\n",
pers->free(mddev, mddev->private);
mddev->private = NULL;
module_put(pers->owner);
- bitmap_destroy(mddev);
- return err;
+ md_bitmap_destroy(mddev);
+ goto abort;
}
if (mddev->queue) {
bool nonrot = true;
err = md_run(mddev);
if (err)
goto out;
- err = bitmap_load(mddev);
+ err = md_bitmap_load(mddev);
if (err) {
- bitmap_destroy(mddev);
+ md_bitmap_destroy(mddev);
goto out;
}
mddev->pers->quiesce(mddev, 1);
mddev->pers->quiesce(mddev, 0);
}
- bitmap_flush(mddev);
+ md_bitmap_flush(mddev);
if (mddev->ro == 0 &&
((!mddev->in_sync && !mddev_is_clustered(mddev)) ||
static void mddev_detach(struct mddev *mddev)
{
- bitmap_wait_behind_writes(mddev);
+ md_bitmap_wait_behind_writes(mddev);
if (mddev->pers && mddev->pers->quiesce) {
mddev->pers->quiesce(mddev, 1);
mddev->pers->quiesce(mddev, 0);
static void __md_stop(struct mddev *mddev)
{
struct md_personality *pers = mddev->pers;
- bitmap_destroy(mddev);
+ md_bitmap_destroy(mddev);
mddev_detach(mddev);
/* Ensure ->event_work is done */
flush_workqueue(md_misc_wq);
mddev->to_remove = &md_redundancy_group;
module_put(pers->owner);
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-}
-
-void md_stop(struct mddev *mddev)
-{
- /* stop the array and free an attached data structures.
- * This is called from dm-raid
- */
- __md_stop(mddev);
if (mddev->flush_bio_pool) {
mempool_destroy(mddev->flush_bio_pool);
mddev->flush_bio_pool = NULL;
mempool_destroy(mddev->flush_pool);
mddev->flush_pool = NULL;
}
+}
+
+void md_stop(struct mddev *mddev)
+{
+ /* stop the array and free an attached data structures.
+ * This is called from dm-raid
+ */
+ __md_stop(mddev);
bioset_exit(&mddev->bio_set);
bioset_exit(&mddev->sync_set);
}
if (fd >= 0) {
struct bitmap *bitmap;
- bitmap = bitmap_create(mddev, -1);
+ bitmap = md_bitmap_create(mddev, -1);
mddev_suspend(mddev);
if (!IS_ERR(bitmap)) {
mddev->bitmap = bitmap;
- err = bitmap_load(mddev);
+ err = md_bitmap_load(mddev);
} else
err = PTR_ERR(bitmap);
if (err) {
- bitmap_destroy(mddev);
+ md_bitmap_destroy(mddev);
fd = -1;
}
mddev_resume(mddev);
} else if (fd < 0) {
mddev_suspend(mddev);
- bitmap_destroy(mddev);
+ md_bitmap_destroy(mddev);
mddev_resume(mddev);
}
}
mddev->bitmap_info.default_offset;
mddev->bitmap_info.space =
mddev->bitmap_info.default_space;
- bitmap = bitmap_create(mddev, -1);
+ bitmap = md_bitmap_create(mddev, -1);
mddev_suspend(mddev);
if (!IS_ERR(bitmap)) {
mddev->bitmap = bitmap;
- rv = bitmap_load(mddev);
+ rv = md_bitmap_load(mddev);
} else
rv = PTR_ERR(bitmap);
if (rv)
- bitmap_destroy(mddev);
+ md_bitmap_destroy(mddev);
mddev_resume(mddev);
} else {
/* remove the bitmap */
md_cluster_ops->leave(mddev);
}
mddev_suspend(mddev);
- bitmap_destroy(mddev);
+ md_bitmap_destroy(mddev);
mddev_resume(mddev);
mddev->bitmap_info.offset = 0;
}
resync -= atomic_read(&mddev->recovery_active);
if (resync == 0) {
+ if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery)) {
+ struct md_rdev *rdev;
+
+ rdev_for_each(rdev, mddev)
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(Faulty, &rdev->flags) &&
+ rdev->recovery_offset != MaxSector &&
+ rdev->recovery_offset) {
+ seq_printf(seq, "\trecover=REMOTE");
+ return 1;
+ }
+ if (mddev->reshape_position != MaxSector)
+ seq_printf(seq, "\treshape=REMOTE");
+ else
+ seq_printf(seq, "\tresync=REMOTE");
+ return 1;
+ }
if (mddev->recovery_cp < MaxSector) {
seq_printf(seq, "\tresync=PENDING");
return 1;
} else
seq_printf(seq, "\n ");
- bitmap_status(seq, mddev->bitmap);
+ md_bitmap_status(seq, mddev->bitmap);
seq_printf(seq, "\n");
}
rcu_read_lock();
rdev_for_each_rcu(rdev, mddev) {
struct gendisk *disk = rdev->bdev->bd_contains->bd_disk;
- curr_events = (int)part_stat_read(&disk->part0, sectors[0]) +
- (int)part_stat_read(&disk->part0, sectors[1]) -
+ curr_events = (int)part_stat_read_accum(&disk->part0, sectors) -
atomic_read(&disk->sync_io);
/* sync IO will cause sync_io to increase before the disk_stats
* as sync_io is counted when a request starts, and
else if (!mddev->bitmap)
j = mddev->recovery_cp;
- } else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+ } else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) {
max_sectors = mddev->resync_max_sectors;
- else {
+ /*
+ * If the original node aborts reshaping then we continue the
+ * reshaping, so set j again to avoid restart reshape from the
+ * first beginning
+ */
+ if (mddev_is_clustered(mddev) &&
+ mddev->reshape_position != MaxSector)
+ j = mddev->reshape_position;
+ } else {
/* recovery follows the physical size of devices */
max_sectors = mddev->dev_sectors;
j = MaxSector;
mddev_lock_nointr(mddev);
md_set_array_sectors(mddev, mddev->pers->size(mddev, 0, 0));
mddev_unlock(mddev);
- set_capacity(mddev->gendisk, mddev->array_sectors);
- revalidate_disk(mddev->gendisk);
+ if (!mddev_is_clustered(mddev)) {
+ set_capacity(mddev->gendisk, mddev->array_sectors);
+ revalidate_disk(mddev->gendisk);
+ }
}
spin_lock(&mddev->lock);
*/
void md_check_recovery(struct mddev *mddev)
{
+ if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags) && mddev->sb_flags) {
+ /* Write superblock - thread that called mddev_suspend()
+ * holds reconfig_mutex for us.
+ */
+ set_bit(MD_UPDATING_SB, &mddev->flags);
+ smp_mb__after_atomic();
+ if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags))
+ md_update_sb(mddev, 0);
+ clear_bit_unlock(MD_UPDATING_SB, &mddev->flags);
+ wake_up(&mddev->sb_wait);
+ }
+
if (mddev->suspended)
return;
if (mddev->bitmap)
- bitmap_daemon_work(mddev);
+ md_bitmap_daemon_work(mddev);
if (signal_pending(current)) {
if (mddev->pers->sync_request && !mddev->external) {
* which has the bitmap stored on all devices.
* So make sure all bitmap pages get written
*/
- bitmap_write_all(mddev->bitmap);
+ md_bitmap_write_all(mddev->bitmap);
}
INIT_WORK(&mddev->del_work, md_start_sync);
queue_work(md_misc_wq, &mddev->del_work);
unlock:
wake_up(&mddev->sb_wait);
mddev_unlock(mddev);
- } else if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags) && mddev->sb_flags) {
- /* Write superblock - thread that called mddev_suspend()
- * holds reconfig_mutex for us.
- */
- set_bit(MD_UPDATING_SB, &mddev->flags);
- smp_mb__after_atomic();
- if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags))
- md_update_sb(mddev, 0);
- clear_bit_unlock(MD_UPDATING_SB, &mddev->flags);
- wake_up(&mddev->sb_wait);
}
}
EXPORT_SYMBOL(md_check_recovery);
void md_reap_sync_thread(struct mddev *mddev)
{
struct md_rdev *rdev;
+ sector_t old_dev_sectors = mddev->dev_sectors;
+ bool is_reshaped = false;
/* resync has finished, collect result */
md_unregister_thread(&mddev->sync_thread);
}
}
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
- mddev->pers->finish_reshape)
+ mddev->pers->finish_reshape) {
mddev->pers->finish_reshape(mddev);
+ if (mddev_is_clustered(mddev))
+ is_reshaped = true;
+ }
/* If array is no-longer degraded, then any saved_raid_disk
* information must be scrapped.
clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+ /*
+ * We call md_cluster_ops->update_size here because sync_size could
+ * be changed by md_update_sb, and MD_RECOVERY_RESHAPE is cleared,
+ * so it is time to update size across cluster.
+ */
+ if (mddev_is_clustered(mddev) && is_reshaped
+ && !test_bit(MD_CLOSING, &mddev->flags))
+ md_cluster_ops->update_size(mddev, old_dev_sectors);
wake_up(&resync_wait);
/* flag recovery needed just to double check */
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
if (ret)
pr_info("md-cluster: resize failed\n");
else
- bitmap_update_sb(mddev->bitmap);
+ md_bitmap_update_sb(mddev->bitmap);
}
/* Check for change of roles in the active devices */
}
if (role != rdev2->raid_disk) {
- /* got activated */
- if (rdev2->raid_disk == -1 && role != 0xffff) {
+ /*
+ * got activated except reshape is happening.
+ */
+ if (rdev2->raid_disk == -1 && role != 0xffff &&
+ !(le32_to_cpu(sb->feature_map) &
+ MD_FEATURE_RESHAPE_ACTIVE)) {
rdev2->saved_raid_disk = role;
ret = remove_and_add_spares(mddev, rdev2);
pr_info("Activated spare: %s\n",
if (mddev->raid_disks != le32_to_cpu(sb->raid_disks))
update_raid_disks(mddev, le32_to_cpu(sb->raid_disks));
+ /*
+ * Since mddev->delta_disks has already updated in update_raid_disks,
+ * so it is time to check reshape.
+ */
+ if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery) &&
+ (le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) {
+ /*
+ * reshape is happening in the remote node, we need to
+ * update reshape_position and call start_reshape.
+ */
+ mddev->reshape_position = sb->reshape_position;
+ if (mddev->pers->update_reshape_pos)
+ mddev->pers->update_reshape_pos(mddev);
+ if (mddev->pers->start_reshape)
+ mddev->pers->start_reshape(mddev);
+ } else if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery) &&
+ mddev->reshape_position != MaxSector &&
+ !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) {
+ /* reshape is just done in another node. */
+ mddev->reshape_position = MaxSector;
+ if (mddev->pers->update_reshape_pos)
+ mddev->pers->update_reshape_pos(mddev);
+ }
+
/* Finally set the event to be up to date */
mddev->events = le64_to_cpu(sb->events);
}
projects / linux.git / blobdiff